EN

EN: All Original content in this blog is now tagged with Original Content DE: Alle originär aus diesem Blog stammenden Inhalte sind nun mit Original Content verschlagwortet.

Update on 20th of March 2026, found on heise.de Initially found on arstechnica.com Update on the 23rd of August 2025 based in information from heise.de. Today there are only four general web search indexes in the western hemisphere and a new european one was anounced on the 7th of August 2025:

EN: Found on heise.de. After all coding assistants are also coming for Databricks: Databricks Blog anouncement: Introducing Genie Code Press release: Databricks Launches Genie Code: Bringing Agentic Engineering to Data Work Overview intro video Get to know video with pipelines: Get to know

Found on theregister.com Test driven development (TDD) produces much better results with AI coding assistants: TDD prevents a failure mode where agents write tests that verify broken behavior. When the tests exist before the code, agents cannot cheat by writing a test that simply confirms whatever

Found on google.com after search for "What are the different RAG methods to minimize confabulation?" Before model context protocol MCP and other agentic context enhancement protocols retrieval augmented generation or RAG was the most important tool to add and extend context on order to minimize

Found on google.com after search for "What are the different sources of bias in AI models?" What are the different sources of bias in AI models? Training data bias Historical data --> historical bias Sampling --> representation bias (stereotyping, recognition, denigration,

If a windows update destroyed your normal grub startup and you are landing in grub rescue you can quite easily restore the grub menu and repair your linux windows dual boot setup. Following steps from today's google AI search summary worked for me: Manual Boot Steps from GRUB Rescue If you are

Found on theregister.com A feature regarding Geoff Huntley, his invention of the Ralph Wiggum Loop and the state of coding and agile: Developers, he argues, should now spend more time thinking about writing loops that drive coding assistants to produce better output, rather than persisting with code reviews.

Found on Daniel Lemures Blog linked by Simon Wilson At the beginning of December 2025 I found on Simon Wilsons blog a link to an interesting post of Daniel Lemure, where he describes why speed matters in science. I fully go with his arguments A common mistake is to spend a lot of time—too much

The AI world clocks by Brian Moore is a good demonstration on how good AI is on creating graphical elements right now. Every minute, there are 9 new clocks displayed, which are generated by nine different AI models. Each model is allowed to use 2000 tokens to generate its clock. Here his prompt: